Bayesian Binomial Regression: Predicting Survival at a Trauma Center

Edward J. Bedrick; Ronald Christensen; Wesley Johnson

doi:10.1080/00031305.1997.10473965

Bayesian Binomial Regression: Predicting Survival at a Trauma Center

Edward J. Bedrick, Ronald Christensen, Wesley Johnson

Research output: Contribution to journal › Article › peer-review

63 Scopus citations

Abstract

Standard methods for analyzing binomial regression data rely on asymptotic inferences. Bayesian methods can be performed using simple computations, and they apply for any sample size. We provide a relatively complete discussion of Bayesian inferences for binomial regression with emphasis on inferences for the probability of “success.” Furthermore, we illustrate diagnostic tools, perform model selection among nonnested models, and examine the sensitivity of the Bayesian methods.

Original language	English (US)
Pages (from-to)	211-218
Number of pages	8
Journal	American Statistician
Volume	51
Issue number	3
DOIs	https://doi.org/10.1080/00031305.1997.10473965
State	Published - Aug 1997
Externally published	Yes

Keywords

Bayesian analysis
Importance sampling
Kullback–Leibler divergence
Logistic regression
Model selection
Prediction
Probit analysis
Regression diagnostics

ASJC Scopus subject areas

Statistics and Probability
General Mathematics
Statistics, Probability and Uncertainty

Access to Document

10.1080/00031305.1997.10473965

Cite this

@article{9d1d540b448f4507b05d1ba84afbecba,

title = "Bayesian Binomial Regression: Predicting Survival at a Trauma Center",

abstract = "Standard methods for analyzing binomial regression data rely on asymptotic inferences. Bayesian methods can be performed using simple computations, and they apply for any sample size. We provide a relatively complete discussion of Bayesian inferences for binomial regression with emphasis on inferences for the probability of “success.” Furthermore, we illustrate diagnostic tools, perform model selection among nonnested models, and examine the sensitivity of the Bayesian methods.",

keywords = "Bayesian analysis, Importance sampling, Kullback–Leibler divergence, Logistic regression, Model selection, Prediction, Probit analysis, Regression diagnostics",

author = "Bedrick, {Edward J.} and Ronald Christensen and Wesley Johnson",

year = "1997",

month = aug,

doi = "10.1080/00031305.1997.10473965",

language = "English (US)",

volume = "51",

pages = "211--218",

journal = "American Statistician",

issn = "0003-1305",

publisher = "American Statistical Association",

number = "3",

}

TY - JOUR

T1 - Bayesian Binomial Regression

T2 - Predicting Survival at a Trauma Center

AU - Bedrick, Edward J.

AU - Christensen, Ronald

AU - Johnson, Wesley

PY - 1997/8

Y1 - 1997/8

N2 - Standard methods for analyzing binomial regression data rely on asymptotic inferences. Bayesian methods can be performed using simple computations, and they apply for any sample size. We provide a relatively complete discussion of Bayesian inferences for binomial regression with emphasis on inferences for the probability of “success.” Furthermore, we illustrate diagnostic tools, perform model selection among nonnested models, and examine the sensitivity of the Bayesian methods.

AB - Standard methods for analyzing binomial regression data rely on asymptotic inferences. Bayesian methods can be performed using simple computations, and they apply for any sample size. We provide a relatively complete discussion of Bayesian inferences for binomial regression with emphasis on inferences for the probability of “success.” Furthermore, we illustrate diagnostic tools, perform model selection among nonnested models, and examine the sensitivity of the Bayesian methods.

KW - Bayesian analysis

KW - Importance sampling

KW - Kullback–Leibler divergence

KW - Logistic regression

KW - Model selection

KW - Prediction

KW - Probit analysis

KW - Regression diagnostics

UR - http://www.scopus.com/inward/record.url?scp=0031531928&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031531928&partnerID=8YFLogxK

U2 - 10.1080/00031305.1997.10473965

DO - 10.1080/00031305.1997.10473965

M3 - Article

AN - SCOPUS:0031531928

SN - 0003-1305

VL - 51

SP - 211

EP - 218

JO - American Statistician

JF - American Statistician

IS - 3

ER -

Bayesian Binomial Regression: Predicting Survival at a Trauma Center

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this